autolearn
by autolearnai
Overview
AutoLearn is an MCP (Model Context Protocol) server that enables AI agents to dynamically create, improve, and execute Python skills (functional code workflows) from natural language, with real-time updates and persistence.
Installation
python demo.pyEnvironment Variables
- OPENAI_API_KEY
- OPENAI_MODEL
- LOG_LEVEL
- DB_PATH
Security Notes
CRITICAL VULNERABILITY: The `backend/sandbox.py` explicitly logs a warning stating 'Executing skill {skill_name} directly (no sandbox) due to pickling limitations'. This means dynamically generated and executed Python code has full access to the underlying server environment, which is an extreme security risk. Additionally, `exec()` is used directly in `backend/skill_engine.py` with code from potentially untrusted AI generation. The CORS `allow_origins=['*']` in `backend/app.py` is also a significant production risk, although noted as a demo setting.
Similar Servers
zeromcp
A minimal, pure Python Model Context Protocol (MCP) server for exposing tools, resources, and prompts via HTTP/SSE and Stdio transports.
mcpc
A framework for building agentic Model Context Protocol (MCP) servers by composing existing MCP tools. It enables the creation of portable, interoperable AI agents with flexible execution modes and robust logging/tracing capabilities.
mcp-mcp
A Meta-MCP server to discover, suggest, and potentially provision other Model Context Protocol (MCP) servers for AI assistants.
MCP-Agent
An AI agent for discovering, connecting to, and interacting with Model Context Protocol (MCP) servers and their provided tools, resources, and prompts.